Files
DEMO-AGENT/tests/test_knowledge_base.py

346 lines
13 KiB
Python

import pytest
from django.core.files.uploadedfile import SimpleUploadedFile
from django.urls import reverse
from review_agent.knowledge_base import (
build_knowledge_base_context,
delete_document,
index_managed_document,
search_knowledge_base,
update_document,
)
from review_agent.views import rebuild_knowledge_base_index
from review_agent.models import KnowledgeBaseDocument
pytestmark = pytest.mark.django_db
def test_knowledge_base_context_reports_rule_and_sources():
context = build_knowledge_base_context()
assert context["rule"]["code"] == "nmpa_ivd_registration_v1"
assert context["rule"]["requirement_count"] > 0
assert context["source_count"] > 0
assert context["collection_name"] == "nmpa_ivd_registration_v1"
assert not any("模拟题二" in source["relative_path"] for source in context["sources"])
def test_knowledge_base_page_requires_login(client):
response = client.get(reverse("knowledge_base_manager"))
assert response.status_code == 302
def test_knowledge_base_page_renders_for_user(client, django_user_model):
user = django_user_model.objects.create_user(username="owner", password="pass")
client.force_login(user)
response = client.get(reverse("knowledge_base_manager"))
assert response.status_code == 200
assert "知识库管理" in response.content.decode("utf-8")
assert "RAG 检索测试" in response.content.decode("utf-8")
content = response.content.decode("utf-8")
tabbar = content[content.index('<div class="tabbar"') : content.index("</div>", content.index('<div class="tabbar"'))]
assert tabbar.index("审核智能体") < tabbar.index("知识库管理") < tabbar.index("附件管理")
assert "data-rebuild-url=" in content
assert 'id="knowledgeRebuildIndexButton"' in content
assert "重建索引" in content
assert 'data-source-action="index"' in content
assert "手动入库" in content
def test_knowledge_base_status_api(client, django_user_model):
user = django_user_model.objects.create_user(username="owner", password="pass")
client.force_login(user)
response = client.get(reverse("knowledge_base_status"))
assert response.status_code == 200
assert response.json()["rule"]["code"] == "nmpa_ivd_registration_v1"
def test_knowledge_base_rebuild_index_api(client, django_user_model, monkeypatch):
user = django_user_model.objects.create_user(username="owner", password="pass")
client.force_login(user)
calls = []
monkeypatch.setattr(
"review_agent.views.rebuild_knowledge_base_index",
lambda: calls.append("rebuild") or {"chunk_count": 12},
)
response = client.post(reverse("knowledge_base_rebuild_index"))
assert response.status_code == 200
assert response.json()["chunk_count"] == 12
assert response.json()["knowledge_base"]["collection"]["count"] >= 0
assert calls == ["rebuild"]
def test_rebuild_knowledge_base_index_requests_reset(settings, tmp_path, monkeypatch):
settings.MEDIA_ROOT = tmp_path
settings.REGULATORY_RAG_CHROMA_PATH = tmp_path / "chroma"
settings.REGULATORY_RAG_CHROMA_PATH.mkdir()
stale_file = settings.REGULATORY_RAG_CHROMA_PATH / "chroma.sqlite3"
stale_file.write_text("stale", encoding="utf-8")
calls = []
monkeypatch.setattr("review_agent.views.load_rule_file", lambda: {"source_material_dir": "docs/0.原始材料"})
monkeypatch.setattr("review_agent.views.get_embedding_provider", lambda: "provider")
monkeypatch.setattr(
"review_agent.views.build_chroma_index",
lambda source_dir, embedding_provider, reset=False: calls.append(
{
"source_dir": source_dir,
"embedding_provider": embedding_provider,
"reset": reset,
}
)
or 8,
)
payload = rebuild_knowledge_base_index()
assert payload["chunk_count"] == 8
assert calls[0]["embedding_provider"] == "provider"
assert calls[0]["reset"] is True
def test_knowledge_base_search_rejects_blank_query():
payload = search_knowledge_base("")
assert payload["results"] == []
assert "请输入" in payload["error_message"]
def test_knowledge_base_search_filters_deleted_managed_documents(monkeypatch, django_user_model):
user = django_user_model.objects.create_user(username="owner", password="pass")
deleted_document = KnowledgeBaseDocument.objects.create(
user=user,
display_name="孙之烨简历",
original_name="孙之烨-260510.pdf",
storage_path="knowledge_base/resume.pdf",
file_size=1,
status=KnowledgeBaseDocument.Status.DELETED,
is_active=False,
indexed_chunk_count=7,
)
monkeypatch.setattr(
"review_agent.knowledge_base.retrieve_citations",
lambda *args, **kwargs: [
{
"source": "用户知识库/1/1/孙之烨-260510.pdf",
"text": "孙之烨负责审核智能体项目。",
"score": 0.2,
"metadata": {"source_type": "managed_document", "document_id": deleted_document.pk},
},
{
"source": "法规材料.doc",
"text": "注册检验报告要求。",
"score": 0.3,
"metadata": {"source_type": "regulatory_document"},
},
],
)
payload = search_knowledge_base("孙之烨是谁")
assert [item["source"] for item in payload["results"]] == ["法规材料.doc"]
def test_knowledge_base_search_api_returns_payload(client, django_user_model):
user = django_user_model.objects.create_user(username="owner", password="pass")
client.force_login(user)
response = client.post(reverse("knowledge_base_search"), {"query": "注册检验报告要求"})
assert response.status_code == 200
assert set(response.json()) == {"query", "results", "error_message"}
def test_knowledge_base_document_crud_api(client, settings, tmp_path, django_user_model):
settings.MEDIA_ROOT = tmp_path
settings.REGULATORY_RAG_CHROMA_PATH = tmp_path / "chroma"
settings.REGULATORY_RAG_PROVIDER = "deterministic"
user = django_user_model.objects.create_user(username="owner", password="pass")
client.force_login(user)
upload_response = client.post(
reverse("knowledge_base_document_list"),
{
"display_name": "注册检验报告要求",
"description": "用于法规依据检索",
"is_active": "true",
"file": SimpleUploadedFile("report.md", b"# report", content_type="text/markdown"),
},
)
assert upload_response.status_code == 200
document_id = upload_response.json()["document"]["id"]
document = KnowledgeBaseDocument.objects.get(pk=document_id)
assert document.display_name == "注册检验报告要求"
assert document.indexed_chunk_count > 0
list_response = client.get(reverse("knowledge_base_document_list"))
assert list_response.status_code == 200
assert list_response.json()["documents"][0]["display_name"] == "注册检验报告要求"
detail_response = client.get(reverse("knowledge_base_document_detail", args=[document_id]))
assert detail_response.status_code == 200
assert detail_response.json()["document"]["original_name"] == "report.md"
assert "已入库" in detail_response.json()["document"]["indexed_label"]
patch_response = client.patch(
reverse("knowledge_base_document_detail", args=[document_id]),
data='{"display_name": "更新后的法规材料", "is_active": false}',
content_type="application/json",
)
assert patch_response.status_code == 200
assert patch_response.json()["document"]["display_name"] == "更新后的法规材料"
assert patch_response.json()["document"]["is_active"] is False
delete_response = client.delete(reverse("knowledge_base_document_detail", args=[document_id]))
assert delete_response.status_code == 200
assert KnowledgeBaseDocument.objects.get(pk=document_id).status == KnowledgeBaseDocument.Status.DELETED
def test_delete_document_removes_managed_chunks_from_index(monkeypatch, django_user_model):
user = django_user_model.objects.create_user(username="owner", password="pass")
document = KnowledgeBaseDocument.objects.create(
user=user,
display_name="孙之烨简历",
original_name="孙之烨-260510.pdf",
storage_path="knowledge_base/resume.pdf",
file_size=1,
indexed_chunk_count=7,
metadata={"index_status": "indexed", "index_error": ""},
)
deleted_filters = []
class FakeCollection:
def delete(self, where):
deleted_filters.append(where)
monkeypatch.setattr("review_agent.knowledge_base._load_chroma_collection", lambda: FakeCollection())
delete_document(document)
document.refresh_from_db()
assert document.status == KnowledgeBaseDocument.Status.DELETED
assert document.is_active is False
assert document.indexed_chunk_count == 0
assert document.metadata["index_status"] == "deleted"
assert deleted_filters == [{"document_id": document.pk}]
def test_disabling_document_removes_managed_chunks_from_index(monkeypatch, django_user_model):
user = django_user_model.objects.create_user(username="owner", password="pass")
document = KnowledgeBaseDocument.objects.create(
user=user,
display_name="孙之烨简历",
original_name="孙之烨-260510.pdf",
storage_path="knowledge_base/resume.pdf",
file_size=1,
status=KnowledgeBaseDocument.Status.ACTIVE,
is_active=True,
indexed_chunk_count=7,
metadata={"index_status": "indexed", "index_error": ""},
)
deleted_filters = []
class FakeCollection:
def delete(self, where):
deleted_filters.append(where)
monkeypatch.setattr("review_agent.knowledge_base._load_chroma_collection", lambda: FakeCollection())
update_document(document, {"is_active": False})
document.refresh_from_db()
assert document.status == KnowledgeBaseDocument.Status.DISABLED
assert document.is_active is False
assert document.indexed_chunk_count == 0
assert document.metadata["index_status"] == "disabled"
assert deleted_filters == [{"document_id": document.pk}]
def test_inactive_document_manual_index_clears_existing_chunks(monkeypatch, django_user_model):
user = django_user_model.objects.create_user(username="owner", password="pass")
document = KnowledgeBaseDocument.objects.create(
user=user,
display_name="孙之烨简历",
original_name="孙之烨-260510.pdf",
storage_path="knowledge_base/resume.pdf",
file_size=1,
status=KnowledgeBaseDocument.Status.DISABLED,
is_active=False,
indexed_chunk_count=7,
metadata={"index_status": "indexed", "index_error": ""},
)
deleted_filters = []
class FakeCollection:
def delete(self, where):
deleted_filters.append(where)
monkeypatch.setattr("review_agent.knowledge_base._load_chroma_collection", lambda: FakeCollection())
chunk_count = index_managed_document(document)
document.refresh_from_db()
assert chunk_count == 0
assert document.indexed_chunk_count == 0
assert document.metadata["index_status"] == "disabled"
assert deleted_filters == [{"document_id": document.pk}]
def test_knowledge_base_document_api_is_scoped_to_owner(client, django_user_model):
owner = django_user_model.objects.create_user(username="owner", password="pass")
other = django_user_model.objects.create_user(username="other", password="pass")
document = KnowledgeBaseDocument.objects.create(
user=owner,
display_name="法规材料",
original_name="a.md",
storage_path="knowledge_base/a.md",
file_size=1,
)
client.force_login(other)
response = client.patch(
reverse("knowledge_base_document_detail", args=[document.pk]),
data='{"display_name": "越权修改"}',
content_type="application/json",
)
assert response.status_code == 404
def test_knowledge_base_document_manual_index_api(client, settings, tmp_path, django_user_model):
settings.MEDIA_ROOT = tmp_path
settings.REGULATORY_RAG_CHROMA_PATH = tmp_path / "chroma"
settings.REGULATORY_RAG_PROVIDER = "deterministic"
user = django_user_model.objects.create_user(username="owner", password="pass")
client.force_login(user)
source_path = tmp_path / "manual.md"
source_path.write_text("# manual\n注册检验报告要求", encoding="utf-8")
document = KnowledgeBaseDocument.objects.create(
user=user,
display_name="manual.md",
original_name="manual.md",
storage_path=str(source_path),
file_size=source_path.stat().st_size,
indexed_chunk_count=0,
)
response = client.post(reverse("knowledge_base_document_index", args=[document.pk]))
assert response.status_code == 200
document.refresh_from_db()
assert document.indexed_chunk_count > 0
assert "已入库" in response.json()["document"]["indexed_label"]